Method and system for ongoing performance monitoring of a character recognition system

• US 7,280,684 B2
• Filed: 07/30/2003
• Issued: 10/09/2007
• Est. Priority Date: 07/30/2003
• Status: Expired due to Fees

• Current Assignee: Toshiba Global Commerce Solutions Holdings Corporation (Toshiba Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Blair, Brian E., Bui, Tuyen Q.
• Primary Examiner(s): Desire; Gregory M
• Application Number:
  US10/630,299
• Publication Number:
  US 20050025362A1
• Time in Patent Office: 1,532 Days
• Field of Search: 382/139, 382/181, 382/228, 382/229, 382/311, 700/108, 702/182
• US Class Current: 382/139
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

A method and system for monitoring the performance of a character recognition system is disclosed. According to a preferred embodiment, the method comprises utilizing an average confidence score for a plurality of characters for ongoing performance monitoring of the character recognition system, wherein a confidence score indicates a level of confidence that a character is accurately recognized.

Claims

1. A method for monitoring performance of a character recognition system, the method comprising:

utilizing an average confidence score generated for a plurality of characters to provide ongoing performance monitoring of the character recognition system, wherein

a confidence score indicates a level of confidence that a character is accurately recognized, and

utilizing the average confidence score further comprises;

determining a threshold confidence score, wherein the threshold confidence score represents a value greater than a minimum level of acceptable performance for the character recognition system and less than an expected level of performance for a new character recognition system,

comparing the average confidence score to the threshold confidence score, and

indicating to an operator that the character recognition system is in need of service responsive to the average confidence score falling below the threshold confidence score.

2. The method of claim 1, wherein the plurality of characters is recorded on at least one end user document, and the method further comprises:

generating the average confidence score for the plurality of characters prior to utilizing the average confidence score.

3. The method of claim 2, wherein generating the average confidence score further comprises:

reading one or more characters recorded on an end user document;

calculating a confidence score for each of the one or more characters; and

averaging the confidence scores for the one or more characters with confidence scores for all characters previously read over a last set number of end user documents.

4. The method of claim 2, wherein the at least one end user document is a standardized document.

5. The method of claim 4, wherein the standardized document is a bank note or personal check.

6. The method of claim 1, wherein responsive to the average confidence score falling below the threshold confidence score, the method further comprises:

servicing the character recognition system; and

resetting the average confidence score.

7. The method of claim 1, wherein at least one of the plurality of characters is a magnetic ink character recognition (MICR) character.

8. The method of claim 1, wherein the character recognition system is one of a magnetic ink character recognition system, an optical character recognition system, or a combined magnetic ink and optical character recognition system.

9. A computer readable medium encoded with a computer program for monitoring performance of a character recognition system, the computer program comprising computer-executable instructions for:

utilizing an average confidence score generated for a plurality of characters to provide ongoing performance monitoring of the character recognition system, wherein

a confidence score indicates a level of confidence that a character is accurately recognized, and

utilizing the average confidence score further comprises;

determining a threshold confidence score, wherein the threshold confidence score represents a value greater than a minimum level of acceptable performance for the character recognition system and less than an expected level of performance for a new character recognition system,

comparing the average confidence score to the threshold confidence score, and

indicating to an operator that the character recognition system is in need of service responsive to the average confidence score falling below the threshold confidence score.

10. The computer readable medium of claim 9, wherein the plurality of characters is recorded on at least one end user document, and the computer program further comprises computer-executable instructions for:

generating the average confidence score for the plurality of characters prior to utilizing the average confidence score.

11. The computer readable medium of claim 10, wherein generating the average confidence score further comprises:

reading one or more characters recorded on an end user document;

calculating a confidence score for each of the one or more characters; and

averaging the confidence scores for the one or more characters with confidence scores for all characters previously read over a last set number of end user documents.

12. The computer readable medium of claim 10, wherein the at least one end user document is a standardized document.

13. The computer readable medium of claim 12, wherein the standardized document is a bank note or personal check.

14. The computer readable medium of claim 9, wherein responsive to the average confidence score falling below the threshold confidence score, the computer program further comprises computer-executable instructions for:

servicing the character recognition system; and

resetting the average confidence score.

15. The computer readable medium of claim 9, wherein at least one of the plurality of characters is a magnetic ink character recognition (MICR) character.

16. The computer readable medium of claim 9, wherein the character recognition system is one of a magnetic ink character recognition system, an optical character recognition system, or a combined magnetic ink and optical character recognition system.

17. A system for monitoring performance of a character recognition system, the system comprising:

a performance monitoring module that utilizes an average confidence score generated for a plurality of characters to provide ongoing performance monitoring of the character recognition system, wherein

a confidence score indicates a level of confidence that a character is accurately recognized, and

the performance monitoring module utilizes the average confidence score by

determining a threshold confidence score, wherein the threshold confidence score represents a value greater than a minimum level of acceptable performance for the character recognition system and less than an expected level of performance for a new character recognition system,

comparing the average confidence score to the threshold confidence score, and

indicating to an operator that the character recognition system is in need of service responsive to the average confidence score falling below the threshold confidence score.

18. The system of claim 17, wherein the plurality of characters is recorded on at least one end user document, and the performance monitoring module further generates the average confidence score for the plurality of characters prior to utilizing the average confidence score.

19. The system of claim 18, further comprising:

means for reading one or more characters recorded on an end user document; and

a decode module that calculates a confidence score for each of the one or more characters,

wherein the performance monitoring module generates the average confidence score by averaging the confidence scores for the one or more characters with confidence scores for all characters previously read over a last set number of end user documents.

20. The system of claim 19, wherein the means for reading the one or more characters comprises one of an optical scanner, a magnetic read head, or a combined optical scanner and magnetic read head.

21. The system of claim 18, wherein the at least one end user document is a standardized document.

22. The system of claim 21, wherein the standardized document is a bank note or personal check.

23. The system of claim 17, wherein at least one of the plurality of characters is a magnetic ink character recognition (MICR) character.

24. A method for monitoring performance of a character recognition system, the method comprising:

utilizing a median confidence score generated for a plurality of characters to provide ongoing performance monitoring of the character recognition system, wherein

a confidence score indicates a level of confidence that a character is accurately recognized, and

utilizing the median confidence score further comprises;

determining a threshold confidence score, wherein the threshold confidence score represents a value greater than a minimum level of acceptable performance for the character recognition system and less than an expected level of performance for a new character recognition system,

comparing the median confidence score to the threshold confidence score, and

indicating to an operator that the character recognition system is in need of service responsive to the median confidence score falling below the threshold confidence score.

25. The method of claim 24, wherein the plurality of characters is recorded on at least one end user document, and the method further comprises:

generating the median confidence score for the plurality of characters prior to utilizing the median confidence score.

26. The method of claim 25, wherein generating the median confidence score further comprises:

reading one or more characters recorded on an end user document;

calculating a confidence score for each of the one or more characters; and

determining the median confidence score from the confidence scores for the one or more characters and confidence scores for all characters previously read over a last set number of end user documents.

27. The method of claim 25, wherein the at least one end user document is a bank note or personal check.

28. The method of claim 24, wherein responsive to the median confidence score falling below the threshold confidence score, the method further comprises:

servicing the character recognition system; and

resetting the median confidence score.

29. The method of claim 24, wherein at least one of the plurality of characters is a magnetic ink character recognition (MICR) character.

30. The method of claim 24, wherein the character recognition system is one of a magnetic ink character recognition system, an optical character recognition system, or a combined magnetic ink and optical character recognition system.